File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ISIT.2014.6875307
- Scopus: eid_2-s2.0-84906551627
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Determining the convergence of variance in Gaussian belief propagation via semi-definite programming
Title | Determining the convergence of variance in Gaussian belief propagation via semi-definite programming |
---|---|
Authors | |
Issue Date | 2014 |
Publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000369 |
Citation | The 2014 IEEE International Symposium on Information Theory (ISIT), Honolulu, HI., 29 June-4 July 2014. In IEEE International Symposium on Information Theory Proceedings, 2014, p. 2614-2618 How to Cite? |
Abstract | In order to compute the marginal distribution from a high dimensional distribution with loopy Gaussian belief propagation (BP), it is important to determine whether Gaussian BP would converge. In general, the convergence condition for Gaussian BP variance and mean are not necessarily the same, and this paper focuses on the convergence condition of Gaussian BP variance. In particular, by describing the message-passing process of Gaussian BP as a set of updating functions, the necessary and sufficient convergence condition of Gaussian BP variance is derived, with the converged variance proved to be independent of the initialization as long as it is greater or equal to zero. It is further proved that the convergence condition can be verified efficiently by solving a semi-definite programming (SDP) optimization problem. Numerical examples are presented to corroborate the established theories. |
Persistent Identifier | http://hdl.handle.net/10722/199396 |
ISBN | |
ISSN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Su, Q | en_US |
dc.contributor.author | Wu, YC | en_US |
dc.date.accessioned | 2014-07-22T01:15:41Z | - |
dc.date.available | 2014-07-22T01:15:41Z | - |
dc.date.issued | 2014 | en_US |
dc.identifier.citation | The 2014 IEEE International Symposium on Information Theory (ISIT), Honolulu, HI., 29 June-4 July 2014. In IEEE International Symposium on Information Theory Proceedings, 2014, p. 2614-2618 | en_US |
dc.identifier.isbn | 978-1-4799-5186-4 | - |
dc.identifier.issn | 0271-4655 | - |
dc.identifier.uri | http://hdl.handle.net/10722/199396 | - |
dc.description.abstract | In order to compute the marginal distribution from a high dimensional distribution with loopy Gaussian belief propagation (BP), it is important to determine whether Gaussian BP would converge. In general, the convergence condition for Gaussian BP variance and mean are not necessarily the same, and this paper focuses on the convergence condition of Gaussian BP variance. In particular, by describing the message-passing process of Gaussian BP as a set of updating functions, the necessary and sufficient convergence condition of Gaussian BP variance is derived, with the converged variance proved to be independent of the initialization as long as it is greater or equal to zero. It is further proved that the convergence condition can be verified efficiently by solving a semi-definite programming (SDP) optimization problem. Numerical examples are presented to corroborate the established theories. | en_US |
dc.language | eng | en_US |
dc.publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000369 | - |
dc.relation.ispartof | IEEE International Symposium on Information Theory Proceedings | en_US |
dc.title | Determining the convergence of variance in Gaussian belief propagation via semi-definite programming | en_US |
dc.type | Conference_Paper | en_US |
dc.identifier.email | Wu, YC: ycwu@hkucc.hku.hk | en_US |
dc.identifier.authority | Wu, YC=rp00195 | en_US |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ISIT.2014.6875307 | - |
dc.identifier.scopus | eid_2-s2.0-84906551627 | - |
dc.identifier.hkuros | 231481 | en_US |
dc.identifier.spage | 2614 | - |
dc.identifier.epage | 2618 | - |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 140821 | - |
dc.identifier.issnl | 0271-4655 | - |